As a leader in innovative health solutions, George Mason University’s College of Public Health has received a grant from the National Institutes of Health (NIH) AIM-AHEAD program to pilot an artificial intelligence (AI) chatbot for Black and African Americans with depression. Professor Farrokh Alemi will enhance his first-of-its-kind, evidence-based AI tool to address the medication needs of African Americans with depression.
The existing AI tool recommends antidepressants for 16,775 patient subgroups in the general population, each representing a unique combination of medical histories. For each of these subgroups, the current project will analyze the effectiveness and appropriateness of the recommendations for African Americans, using the NIH’s All of Us database and existing published literature.
To the researchers’ knowledge, this is the first research focused on the development and evaluation of an antidepressant recommendation system for black and African-American people.
“Antidepressants are the first-line treatment for depression. However, the majority of depressed patients do not see improvement with their first antidepressant. Additionally, minority populations, including Blacks and African Americans, are underrepresented in antidepressant studies, contributing to the reduced effectiveness of antidepressants in these populations,” Alemi said. “It is imperative to synthesize the available data on the effectiveness of antidepressants and provide personalized treatment recommendations. This project fills a major gap in the care of Blacks and African Americans with depression.”
The researchers will develop a knowledge-enhanced antidepressant recommendation dialogue system (KARDS), which will engage users in a back-and-forth conversation to elicit the information the patient needs to identify the appropriate antidepressant medication. The AI will provide the patient with a list of recommended medications, a list of relevant studies, and an explanation of medication decisions. The system will automatically send the patient’s clinician a brief recommendation and explanation at the point of care, with an option to review a full account of the conversation and supporting evidence.
“Chatbots, or patient dialogue systems like the one we will create, have transformative potential for the healthcare industry and are increasingly present in psychiatric applications, primarily through therapeutic robot implementations,” Alemi said. “Our chatbot will help improve the detailed and time-consuming process of taking medical history and provide a summary and prescription recommendations to patients’ clinicians. The chatbot will put patients at ease because the natural language modality offers an intuitive, empathetic and stigma-free interface.”
Once the AI chatbot is developed, the team will test the dialogue system with Black and African American patients to assess the system’s features and usage preferences. Additionally, the project will train a Black or African American PhD or master’s student in AI, expanding the available workforce and building the community’s capacity to address AI.
Alemi will lead the research team, which includes Janusz Wojtusiak, George Mason professor of medical informatics and director of the Machine Learning and Inference Lab, and Kevin Lybarger, George Mason assistant professor in the Department of Information Science and Technology in the College of Engineering and Computing. The three have previously collaborated to diagnose COVID at home based on symptoms.
The $70,906 grant comes from the NIH’s Artificial Intelligence/Machine Learning Consortium to Advance Health Equity and Researcher Diversity (AIM-AHEAD) program, which aims to “establish mutually beneficial and coordinated partnerships to increase the participation and representation of researchers and communities currently underrepresented in AI/machine learning model development and enhance the capabilities of this emerging technology, beginning with electronic health record data.”
Innovate for Good is an ongoing series that examines how George Mason faculty in the College of Public Health are leveraging technology to improve health outcomes.
If you have stories to share as part of the Innovate for Good series, email Mary Cunningham at mcunni7@gmu.edu.
